Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fatihguner/foreman --skill ai-augmentation-not-automationgit clone --depth 1 https://github.com/fatihguner/foremanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation)<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-augmentation-not-automation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-augmentation-not-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00120 | $0.04448 |
| Opus 5 | $0.00060 | $0.02224 |
| Sonnet 5 | $0.00024 | $0.00890 |
| Haiku 4.5 | $0.00012 | $0.00445 |
Grade A, and why
ai-augmentation-not-automation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
AI Augmentation, Not Automation
In 2005, the online chess platform Playchess.com hosted a freestyle tournament with an unusual rule: any combination of humans and computers could enter. Grandmasters played alongside AI engines and hybrid teams of amateurs armed with laptops. The winners were not the grandmasters. They were not the strongest AI engines. They were two amateur players using three ordinary computers, who had developed a superior process for integrating human intuition with machine calculation. Garry Kasparov, observing the result, articulated the principle that would come to define a generation of human-AI research: "Weak human + machine + better process was superior to a strong computer alone and, remarkably, superior to a strong human + machine + inferior process." The centaur -- the mythological creature that is half human, half horse, greater than either -- had entered the business lexicon. The principle applies directly to every organisation contemplating AI: the goal is not to replace the human with the machine but to create a hybrid that outperforms both.
The Framework
The Automation Trap
Up to 60 percent of work activities could be automated, and this trend shows no signs of decelerating. Organisations pursue standardisation, streamlining, and speed. From a short-term financial perspective, automation is compelling: lower labour costs, consistent output, no sick days, no salary negotiations. One executive remarked with evident satisfaction that AI was "an absolute cost killer" for his clients.
The satisfaction is premature. Automation delivers short-term performance gains that mask four structural pathologies, each of which erodes the long-term capability of the organisation.
Pathology 1: Job fragmentation and polarisation. When AI automates the routine middle of the job spectrum -- administrative, bureaucratic, process-driven work -- the result is not a smaller, more skilled workforce. It is a bifurcated one. High-paid creative and strategic roles remain. Low-paid manual roles that are too expensive to automate remain. The middle disappears. Workers displaced from mid-level positions cannot immediately upskill to strategic roles; they fall into lower-paid work. Bargaining power erodes. Inequality increases. The socioeconomic instability that results does not stay outside the company gates -- it becomes the company's operating environment.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · +198 lines · +120 tokens per session e27827c4c172
- 11d ago First seen · 1 lines · 0 tokens per session scan A 97e0b5d065ae
ai-augmentation-not-automation is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session and 4,448 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
creative-ideation
Structured brainstorming sessions using proven ideation techniques.
knowledge-transfer
Cross-Domain Know-How-Transfer — findet kreative Anwendungen von Vault-Expertise in anderen Branchen.
elon-musk
Agente que simula Elon Musk com profundidade psicologica e comunicacional de alta fidelidade. Ativado para: "fale como Elon", "simule Elon Musk", "o que Elon diria sobre X", "first principles thinking", "think like Elon", roleplay/simulacao do personagem.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…